agentsclimarketplace

Code

Skill ronniepinnell/casper/collection/meta-and-tooling/code

👻 The friendly ghost in your git. Your AI said done — Casper makes it prove it. Claim-evidence hooks + a verdict ledger for Claude Code.

Install
npx -y skills add ronniepinnell/casper --skill code

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Build/fix features with test-first development, review, and doc sync.

SKILL.md

1.5 KB, 331 tokens by cl100k_base, as published. Nobody here has run it

/code — Build/Fix Features

Enters CODE mode. Structured implementation with TDD, review, and doc sync.

What Happens

  1. Load context: Read {plan_file}, relevant specs, CLAUDE.md coding rules
  2. Plan: Enter plan mode, identify files to change, get Operator approval
  3. Implement: Write tests first, then code, following .agents/reference/code_modularization.md
  4. Review: Launch code-reviewer + compliance-checker agents
  5. Doc sync: Update docs per config/doc_mappings.json mappings
  6. On /done: Commit, verify gates pass

Team Mode (if CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is set)

Lead Dev + Test Writer + Reviewer + Doc Sync agent.

Fallback Mode (if env var not set)

Sequential subagent calls:

  1. Specialized agent (etl-specialist, dashboard-developer, etc.) for implementation
  2. code-reviewer agent for review
  3. compliance-checker agent for CLAUDE.md adherence
  4. Doc sync in main context

Gate References

  • Gate 2 (pre-commit): Validates any generated prompts
  • Gate 3 (honesty): Verifies claims match actual output

Judgment weave (see /judgment)

  • Bug fixes: run /altitude before coding — land the fix at the cause's layer, not the symptom's.
  • Before claiming done: run /refute on your own completion claim.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.